Description of the Closed Loop of an Object of Interest

To monitor objects of interest, such as wildlife and people, image-capturing devices are used to collect a large number of images with and without objects of interest. As we are recording valuable information about the behavior and activity of objects, the quality of images containing objects of interest should be better than that of images without objects of interest, even if the former exhibits more severe distortion than the latter. However, according to current methods, quality assessments produce the opposite results. In this study, we propose an end-to-end model, named DETR-IQA (detection transformer image quality assessment), which extends the capability to perform object detection and blind image quality assessment (IQA) simultaneously by adding IQA heads comprising simple multi-layer perceptrons at the top of the DETRs (detection transformers) decoder. Using IQA heads, DETR-IQA carried out blind IQAs based on the weighted fusion of the distortion degree of the region of objects of interest and the other regions of the image; the predicted quality score of images containing objects of interest was generally greater than that of images without objects of interest. Currently, the subjective quality score of all public datasets is in accordance with the distortion of images and does not consider objects of interest. We manually extracted the images in which the five predefined classes of objects were the main contents of the largest authentic distortion dataset, KonIQ-10k, which was used as the experimental dataset. The experimental results show that with slight degradation in object detection performance and simple IQA heads, the values of PLCC and SRCC were 0.785 and 0.727, respectively, and exceeded those of some deep learning-based IQA models that are specially designed for only performing IQA. With the negligible increase in the computation and complexity of object detection and without a decrease in inference speeds, DETR-IQA can perform object detection and IQA via multi-tasking and substantially reduce the workload.

Object of Interest (OoI) segmentation in video sequences is, due to its temporal and spatial complexity, still a difficult task. Thus, it cannot be done automatically, and interactive segmentation methods are inconvenient and time-consuming. Overcoming these drawbacks and performing OoI segmentation in real-time, this paper introduces a new approach for gaze-based OoI segmentation. The user fixates on the OoI throughout watching a video sequence. The users’ gaze provides relevant information on the location of the OoI, which is then used for segmenting the OoI. In comparison to present segmentation methods, our approach notably reduced user-interactions required to attain pixel-accurate segmentations. The first evaluation of our gaze-based OoI segmentation method shows promising results. These are close to, and sometimes even exceeding the quality of the polygon-based ground truth segmentation. In conclusion, these findings encourage further exploration of gaze-based OoI segmentation.

Extracting objects of interest in video is a challenging task that can improve the performance of video compression and retrieval. Usually moving objects in video were considered as objects of interest, so there were many researches to extract them. However, we know that some non-moving (static) objects also can be objects of interest. A segmentation method is proposed in this paper, which extracts static objects as well as moving objects that are likely to attract human’s interest. An object of interest is defined as the relatively large region that appears frequently over several frames and is not located near boundaries of the frames. A static object of interest should also have significant color and texture characteristics against its surround. We found that the objects of interest extracted by the proposed method were well matched with the objects of interest selected manually.Keywordsobject of interestvisual attentioncontent-based video retrieval

In computer vision tasks such as, for example, object recognition, semantically accurate segmentation of a particular object of interest (OOI) is a critical step. Due to the OOI consisting of visually different fragments, traditional segmentation algorithms that are based on the identification of homogeneous regions usually do not perform well. In order to narrow this gap between low-level visual features and high-level semantics, some recent methods employ machine learning to generate more accurate models of the OOI. The main contribution of this paper is the inclusion of spatial relationships among the OOI fragments into the model. For this purpose, we employ Bayesian networks as a probabilistic approach for learning the spatial relationships which, in turn, becomes evidence that is used for the process of segmenting future instances of the OOI. The algorithm presented in this paper also uses multiple instance learning to obtain prototypical descriptions of each fragment of the OOI based on low-level visual features. The experimental results on both artificial and real image datasets indicate that the addition of spatial relationships improves segmentation performance.

After the economy, education, health system, culture, society in general were almost completely destroyed in the last decades, the Romanian civilization must be rebuilt, on new foundations, considering top trends. Being a complex action, the reconstruction and relaunching of the country on the way to development could be planned and carried out on the basis of very long-term strategies from which the plans for more and more detailed terms can later be extracted. The strategies must start from fundamental strategic principles that target the major objectives of the national interest, as well as the objectives of interest in the international arena in which the country is involved. From many possible principles, we comment only a few, less discussed, for exemplification.

Computer vision systems majorly work on the basis of capturing three dimensional scenes. The scenes however have two dimensional images or videos that are sent for processing. The said images and the videos always have an object of interest. The scenes which are captured have a number of objects along with the object of interest. of all these objects, the ones which are not required are ignored or considered as the background. Consider applications like tracking and object identification, where the object of interest has to be identified. The computer vision system which captures these scene, has along with other objects, Object of interest and also their shadows. If only the object of interest is considered then its shadow having a shape almost similar to that of the object and further if the object is dark then the matching is at shape as well as colour level. There are always chances that the tracking and the object identification system which works on colour and shape, may detect the shadow in place of the object. This is called as false tracking or false detection respectively. The limitations of the computer vision system is that it cannot differentiate between the objects and its shadows, so a preprocessing stage has to be introduced between the computer vision system and processing stage called as the shadow detection and elimination system. The algorithm for the same maps in four working domain namely intensity, colour, texture and geometry. This paper highlights the colour based method based on global thresholding used for shadow detection with suggested modifications at the local level. This is the work which is presented in this paper. It further uses the qualitative and quantitative evaluation methods to compare the modified method with existing global thresholding method.

Acoustic emission analysis is defined as a passive, non-destructive investigation method, which only listens for AE-waves (AEW), generated actively by an object of interest. Therefore, the AEW must have the possibility to propagate from their source to an acoustic emission sensor (AES). By virtue of the piezoelectric effect, the AEW transmitted into electrical signals inside of the AES. During the analysation of these electrical signals we earn–online–information about the object of interest, e.g. the operating characteristic of a machine or the strength of the friction of a tribolocical system. To enable the AEW to propagate into the AES, the sensor has to be fixed suitable onto the object of interest. Hereby has to be strictly respected, that the sensor is fixed in a reproducible mechanical way as well as to ensure that the through-transmission has a weak attenuation (couplant). Standard AES have the shape of a circular cylinder (diameter and height depend on the operation purpose), the AEW pass through one of the frontends into the sensor. The objects of interest can have different geometry of the surface (e.g. plane, cylindrical, unspecific) or temperatures which usually conflicting the operating range of the sensor. Depending on the operational purpose, there are many different couplants to use. This article offers help to master the different connecting challenges within the range of acoustic emission analysis.

Recently applications involving capture of scenes with object of interest among surroundings gained high popularity. Such applications include video surveillance, human motion capture, human-computer interaction, etc. For proper analysis of the object of interest a necessary step is to separate the object of interest from surroundings, i. e. perform background subtraction (or silhouette extraction). This is a challenging task because of several problems, which are slight changes in background; shadows caused by the object of interest; and similarly colored objects. In this work we propose a new method for extracting the silhouette of an object of interest, based upon the joint use of both depth (range) and color data. Depth-based data is independent of color image data, and hence not affected by the limitations associated with color-based segmentation, such as shadows and similarly colored objects. At the initial moment an image of the background (not containing the object of interest) is present, and it is updated in every frame taking into account extracted silhouette and using "running average". Silhouette extraction method is based on k-means clustering of depth data and color difference data, and per-pixel silhouette mask computation, using clusters' centroids. The proposed solution is very fast and allows real-time processing of video. Developed algorithm has been successfully applied in human recognition application and provided good results for modeling human figure.

Autonomous mobile robotic teams are increasingly used in exploration of indoor environments. Accurate modeling of the world around the robot and describing the interaction of the robot with the world greatly increases the ability of the robot to act autonomously. This paper demonstrates the ability of autonomous robotic teams to find objects of interest. A novel feature of our approach is the object discovery and the use of it to augment the mapping and navigation process. The generated map can then be decomposed into semantic regions while also considering the distance and line of sight to anchor points. The advantage of this approach is that the robot can return a dense map of the region around an object of interest. The robustness of this approach is demonstrated in indoor environments with multiple platforms with the objective of discovering objects of interest.

The visual information of a surveillance system should provide extended and just-in-time perception in monitored environments. However, delivering visual information of surveillance from nonstationary providers, such as mobile cameras, to designated end-users over bandwidth-limited networks is a challenging task. In this paper, for transmitting visual objects of interest, an embedded spatial coding approach is proposed to progressively encode the presentation quality of visual objects under receivers' bandwidth limitation. First, different levels of importance for the objects of interest are characterized by the standard edge detection algorithm and several designated priorities for these objects are progressively assigned. The spatial coding approach then adopts a wavelet-based image coding algorithm based on the assigned priority of each object of interest. Therefore, each individual receiver can adaptively obtain the best visual information of the most important object under its available bandwidth. The proposed priority assignment and spatial coding mechanism has been extensively tested and analyzed. The experimental results show that, under different bandwidth scenarios and required acceptable signal-quality levels, the end-users can obtain the best visual quality of the important objects of interest. Therefore, the importance of the objects of interest in real-time surveillance video can be properly determined and the required transmission quantity can be effectively allocated.

Currently, gradient domain methods are popular for producing seamless cloning of a source image patch into a target image. However, structure conflicts between the source image patch and the target image may generate artifacts, preventing the general practices. In this paper, we tackle the challenge by incorporating the users' intent in outlining the source patch, where the boundary drawn generally has different appearances from the objects of interest. We first reveal that artifacts exist in the over-included region, the region outside the objects of interest in the source patch. Then we use the diversity from the boundary to approximately distinguish the objects from the over-included region, and design a new algorithm to make the target image adaptively take effects in blending. So the structure conflicts can be efficiently suppressed to remove the artifacts around the objects of interest in the composite result. Moreover, we develop an interpolation measure to composite the final image rather than solving a Poisson equation, and speed up the interpolation by treating pixels in clusters and using hierarchical sampling techniques. Our method is simple to use for instant and high-quality image cloning, in which users only need to outline a region of interested objects to process. Our experimental results have demonstrated the effectiveness of our cloning method.

Visual search for objects of interest in complex environment is an important (and still challenging) problem in mobile robotics. In particular, the usage of content-based visual information retrieval (CBVIR) methods, which are a natural choice for such tasks, is often constrained by the real-time requirements, and the mobility of searching agents is sometimes not sufficiently exploited in the search model. In this paper, a CBVIR-based scheme is proposed, which takes into account motion of the searching agents to achieve a low-cost and highspeed detection of objects of interest in cluttered scenes, with good overall performances. We combine standard CBVIR tools, i.e. MSER detector and SIFT descriptor (quantized into sufficiently large vocabularies) assuming additionally that objects become objects of interest only when approached closely enough by the mobile agent, i.e. when seen at an adequately large scale. Thus, an object of interest is considered detected only if a sufficient number of keypoints from the current video-frame are matched (including the corresponding matches of scales) to the keypoints from the database images of the object. Preliminary experiments on a limited-size dataset confirm performances of the scheme, although in the classical task of video-frame retrieval the scheme cannot compete with more sophisticated CBVIR algorithms. The scheme can prospectively become more flexible if combined with a range-finding device so that the approximate distances to the scene components within the currently inspected part of the image can be used to proportionally modify the scale correspondences.

Quantitative analysis of biological microstructures using unbiased stereology plays a large and growing role in bioscience research. Our aim is to add a fully automatic, high-throughput mode to a commercially available, computerized stereology device (Stereologer). The current method for estimation of first- and second order parameters of biological microstructures, requires a trained user to manually select objects of interest (cells, fibers etc.,) while stepping through the depth of a stained tissue section in fixed intervals. The proposed approach uses a combination of color and gray-level processing. Color processing is used to identify the objects of interest, by training on the images to obtain the threshold range for objects of interest. In gray-level processing, a region-growing approach was used to assign a unique identity to the objects of interest and enumerate them. This automatic approach achieved an overall object detection rate of 93.27%. Thus, these results support the view that automatic color and gray-level processing combined with unbiased sampling and assumption and model-free geometric probes can provide accurate and efficient quantification of biological objects.

Object density-based image segmentation and its applications in biomedical image analysis

A mathematical framework is proposed to investigate how different parameters affect the achievable resolution from microwave tomography (MWT). This framework attempts to incorporate multiple scattering events within the object of interest (OI) into its analysis by taking into account the effect of the induced total field within the OI. To this end, a linearized operator, which maps the OI’s permittivity profile to the measured data, is first constructed. The framework then revolves around the number of the right singular vectors of this operator, and their spatial frequency contents that can be utilized in reconstruction. Furthermore, this framework is used to introduce the “best” possible reconstruction that can be achieved in a given MWT system when imaging a typical OI. This concept can then provide some insights and guidelines for MWT system design.